Cleaning the Data
NBA500_new_ranking_system <- read_excel("~/Documents/Syracuse/Term 2/Intro to Data Science/Project/NBA500 new ranking system.xlsx")
NBA500 <- NBA500_new_ranking_system
#Converting to new dataframe
NBA <- NBA500
NBA500[is.na(NBA500)] <- 0
#Changing MVP column name
names(NBA)[3] <- paste("mvp.rank")
#Reordering for MVP
NBA <- NBA[order(NBA$mvp.rank),]
#Creating seperate MVP DF
MVP <- data.frame(NBA[1:13,])
names(MVP)[3] <- paste("mvp.rank")
#Removing MVPs from original DF
NBA <- NBA[-1:-13,]
#Removing mvp.rank col from NBA DF
NBA <- NBA[,-3]
#Changing colnames for MVP
colnames(MVP) <- c("Player","Rk","MVP", "Pos", "Position.number", "Age", "Team", "G", "GS", "MP", "FG", "FGA", "FG.", "3P", "3PA", "3P.", "2P", "2PA", "2P.", "FT", "FTA", "FT.", "ORB", "DRB", "TRB", "AST", "STL", "BLK", "TOV", "PF", "PTS", "ORtg", "DRtg")
#Changing colnames for NBA
colnames(NBA) <- c("Player","Rk","Pos", "Position.number", "Age", "Team", "G", "GS", "MP", "FG", "FGA", "FG.", "3P", "3PA", "3P.", "2P", "2PA", "2P.", "FT", "FTA", "FT.", "ORB", "DRB", "TRB", "AST", "STL", "BLK", "TOV", "PF", "PTS", "ORtg", "DRtg")
#Changing colnames for NBA500
colnames(NBA500) <- c("Player","Rk","MVP", "Pos", "Position.number", "Age", "Team", "G", "GS", "MP", "FG", "FGA", "FG.", "3P", "3PA", "3P.", "2P", "2PA", "2P.", "FT", "FTA", "FT.", "ORB", "DRB", "TRB", "AST", "STL", "BLK", "TOV", "PF", "PTS", "ORtg", "DRtg")
#NBA avg FG%
mean(NBA$FG.)
## [1] 0.4464209
#MVP avg FG%
mean(MVP$FG.)
## [1] 0.4886923
#NBA avg FG
mean(NBA$FG)
## [1] 7.169815
#MVP avg FG
mean(MVP$FG)
## [1] 12.66923
#MVP avg games-started
mean(MVP$GS)
## [1] 71.38462
#NBA avg games-started
mean(NBA$GS)
## [1] 23.34497
#Visuals
##Question 1
#Minutes Played plot
ggplot(NBA500, aes(x=Player, y=MP, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Minutes Played MVP
ggplot(MVP, aes(x=Player, y=MP, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + geom_text(aes(label=Player),hjust=0.60, vjust=-1) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Games Started
ggplot(NBA500, aes(x=Player, y=GS, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Games Started MVP
ggplot(MVP, aes(x=Player, y=GS, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + geom_text(aes(label=Player),hjust=0.60, vjust=-1) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Field Goals
ggplot(NBA500, aes(x=Player, y=FG, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Field Goals MVP
ggplot(MVP, aes(x=Player, y=FG, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + geom_text(aes(label=Player),hjust=0.60, vjust=-1) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Free Throws Attempted
ggplot(NBA500, aes(x=Player, y=FTA, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Free Throws Attempted MVP
ggplot(MVP, aes(x=Player, y=FTA, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + geom_text(aes(label=Player),hjust=0.60, vjust=-1) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Points Scored
ggplot(NBA500, aes(x=Player, y=PTS, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Points Scored MVP
ggplot(MVP, aes(x=Player, y=PTS, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + geom_text(aes(label=Player),hjust=0.60, vjust=-1) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

##Question 2
#ORtg in plot
plot(NBA500$MVP ~ NBA500$ORtg)

#DRtg in plot
plot(NBA500$MVP ~ NBA500$DRtg)

plot(MVP$ORtg ~ MVP$MVP)
plot(MVP$ORtg ~ MVP$MVP)

#Question 3
pbar <- ggplot(data = MVP) +
geom_bar(mapping = aes(x = Pos, fill = Pos), width = 1) +
theme(aspect.ratio = 1) +
labs(x= NULL, y = NULL, title = "Proportion of MVP Eligibility by Position")
#Bar chart to show Positions within MVP status
pbar + coord_flip()

#Pie chart to show Positions within MVP status
pbar + coord_polar()

#Pie chart to show distribution of position based on off number of votes
MVP.Pie <- ggplot(MVP, aes(x= "", y = MVP, fill= Pos)) +
geom_bar(mapping = aes(x = Pos, fill = Pos), stat = "identity", width = 1) +
theme(aspect.ratio = 1, axis.ticks = element_blank()) +
labs(x=NULL, y = NULL, title = "Proportion of MVP Position by Vote Totals") +
coord_polar()
MVP.Pie

# This pie chart shows that although SG and PF both had the same number of players
#within the MVP runnings, PF had more top ranked votes. Therefore it was more beneficial to play the PF position
#Question 4
#Field Goal Percentages
ggplot(NBA500, aes(x=Player, y=FG., group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Field Goal Attempts
ggplot(NBA500, aes(x=Player, y=FGA, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Three Point Percentages
ggplot(NBA500, aes(x=Player, y=`3P.`, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Three Point Attempts
ggplot(NBA500, aes(x=Player, y=`3PA`, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Free Throw Percentages
ggplot(NBA500, aes(x=Player, y=`FT.`, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())

#Free Throw Attempts
ggplot(NBA500, aes(x=Player, y=FTA, group=MVP)) + geom_point(aes(color=MVP, size=MVP)) + theme(axis.line = element_blank(), axis.text = element_blank(), axis.ticks = element_blank())
